Generally Intelligent cover image

Episode 22: Archit Sharma, Stanford, on unsupervised and autonomous reinforcement learning

Generally Intelligent

CHAPTER

I Love That Simple Is Good

I had this idea that, oh, like, if we start incorporating predictability, it's related to some of the current work through base rule. And yeah, I had this idea and was working on it and I said like, I didn't have that much experience making these things work. So then a lot of the struggles related to the project was just like me trying to like get something working. But once it was working, you just kind of like worked out like walks. so it's really simple to get an after like, I understood the nuts and bolts of the algorithms. Yeah. I mean, I love that simple is good. Like you love the simple right.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner